A Survey on LLM Inference-Time Self-Improvement
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910752231653376 |
|---|---|
| author | Dong, Xiangjue Teleki, Maria Caverlee, James |
| author_facet | Dong, Xiangjue Teleki, Maria Caverlee, James |
| contents | Techniques that enhance inference through increased computation at test-time have recently gained attention. In this survey, we investigate the current state of LLM Inference-Time Self-Improvement from three different perspectives: Independent Self-improvement, focusing on enhancements via decoding or sampling methods; Context-Aware Self-Improvement, leveraging additional context or datastore; and Model-Aided Self-Improvement, achieving improvement through model collaboration. We provide a comprehensive review of recent relevant studies, contribute an in-depth taxonomy, and discuss challenges and limitations, offering insights for future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_14352 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Survey on LLM Inference-Time Self-Improvement Dong, Xiangjue Teleki, Maria Caverlee, James Computation and Language Techniques that enhance inference through increased computation at test-time have recently gained attention. In this survey, we investigate the current state of LLM Inference-Time Self-Improvement from three different perspectives: Independent Self-improvement, focusing on enhancements via decoding or sampling methods; Context-Aware Self-Improvement, leveraging additional context or datastore; and Model-Aided Self-Improvement, achieving improvement through model collaboration. We provide a comprehensive review of recent relevant studies, contribute an in-depth taxonomy, and discuss challenges and limitations, offering insights for future research. |
| title | A Survey on LLM Inference-Time Self-Improvement |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2412.14352 |